linux-brain/arch/openrisc/kernel/signal.c

327 lines
8.6 KiB
C
Raw Normal View History

/*
* OpenRISC signal.c
*
* Linux architectural port borrowing liberally from similar works of
* others. All original copyrights apply as per the original source
* declaration.
*
* Modifications for the OpenRISC architecture:
* Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
* Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/errno.h>
#include <linux/wait.h>
#include <linux/ptrace.h>
#include <linux/unistd.h>
#include <linux/stddef.h>
#include <linux/tracehook.h>
#include <asm/processor.h>
#include <asm/syscall.h>
#include <asm/ucontext.h>
#include <linux/uaccess.h>
#define DEBUG_SIG 0
struct rt_sigframe {
struct siginfo info;
struct ucontext uc;
unsigned char retcode[16]; /* trampoline code */
};
static int restore_sigcontext(struct pt_regs *regs,
struct sigcontext __user *sc)
{
int err = 0;
/* Always make any pending restarted system calls return -EINTR */
all arches, signal: move restart_block to struct task_struct If an attacker can cause a controlled kernel stack overflow, overwriting the restart block is a very juicy exploit target. This is because the restart_block is held in the same memory allocation as the kernel stack. Moving the restart block to struct task_struct prevents this exploit by making the restart_block harder to locate. Note that there are other fields in thread_info that are also easy targets, at least on some architectures. It's also a decent simplification, since the restart code is more or less identical on all architectures. [james.hogan@imgtec.com: metag: align thread_info::supervisor_stack] Signed-off-by: Andy Lutomirski <luto@amacapital.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: David Miller <davem@davemloft.net> Acked-by: Richard Weinberger <richard@nod.at> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Matt Turner <mattst88@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Steven Miao <realmz6@gmail.com> Cc: Mark Salter <msalter@redhat.com> Cc: Aurelien Jacquiot <a-jacquiot@ti.com> Cc: Mikael Starvik <starvik@axis.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Tested-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Chris Zankel <chris@zankel.net> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Guenter Roeck <linux@roeck-us.net> Signed-off-by: James Hogan <james.hogan@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-13 08:01:14 +09:00
current->restart_block.fn = do_no_restart_syscall;
/*
* Restore the regs from &sc->regs.
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 11:57:57 +09:00
* (sc is already checked since the sigframe was
* checked in sys_sigreturn previously)
*/
err |= __copy_from_user(regs, sc->regs.gpr, 32 * sizeof(unsigned long));
err |= __copy_from_user(&regs->pc, &sc->regs.pc, sizeof(unsigned long));
err |= __copy_from_user(&regs->sr, &sc->regs.sr, sizeof(unsigned long));
/* make sure the SM-bit is cleared so user-mode cannot fool us */
regs->sr &= ~SPR_SR_SM;
regs->orig_gpr11 = -1; /* Avoid syscall restart checks */
/* TODO: the other ports use regs->orig_XX to disable syscall checks
* after this completes, but we don't use that mechanism. maybe we can
* use it now ?
*/
return err;
}
asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs)
{
struct rt_sigframe *frame = (struct rt_sigframe __user *)regs->sp;
sigset_t set;
/*
* Since we stacked the signal on a dword boundary,
* then frame should be dword aligned here. If it's
* not, then the user is trying to mess with us.
*/
if (((long)frame) & 3)
goto badframe;
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 11:57:57 +09:00
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
goto badframe;
set_current_blocked(&set);
if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
goto badframe;
if (restore_altstack(&frame->uc.uc_stack))
goto badframe;
return regs->gpr[11];
badframe:
force_sig(SIGSEGV);
return 0;
}
/*
* Set up a signal frame.
*/
static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
{
int err = 0;
/* copy the regs */
/* There should be no need to save callee-saved registers here...
* ...but we save them anyway. Revisit this
*/
err |= __copy_to_user(sc->regs.gpr, regs, 32 * sizeof(unsigned long));
err |= __copy_to_user(&sc->regs.pc, &regs->pc, sizeof(unsigned long));
err |= __copy_to_user(&sc->regs.sr, &regs->sr, sizeof(unsigned long));
return err;
}
static inline unsigned long align_sigframe(unsigned long sp)
{
return sp & ~3UL;
}
/*
* Work out where the signal frame should go. It's either on the user stack
* or the alternate stack.
*/
static inline void __user *get_sigframe(struct ksignal *ksig,
struct pt_regs *regs, size_t frame_size)
{
unsigned long sp = regs->sp;
/* redzone */
sp -= STACK_FRAME_OVERHEAD;
sp = sigsp(sp, ksig);
sp = align_sigframe(sp - frame_size);
return (void __user *)sp;
}
/* grab and setup a signal frame.
*
* basically we stack a lot of state info, and arrange for the
* user-mode program to return to the kernel using either a
* trampoline which performs the syscall sigreturn, or a provided
* user-mode trampoline.
*/
static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
struct pt_regs *regs)
{
struct rt_sigframe *frame;
unsigned long return_ip;
int err = 0;
frame = get_sigframe(ksig, regs, sizeof(*frame));
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 11:57:57 +09:00
if (!access_ok(frame, sizeof(*frame)))
return -EFAULT;
/* Create siginfo. */
if (ksig->ka.sa.sa_flags & SA_SIGINFO)
err |= copy_siginfo_to_user(&frame->info, &ksig->info);
/* Create the ucontext. */
err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(NULL, &frame->uc.uc_link);
err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
err |= setup_sigcontext(regs, &frame->uc.uc_mcontext);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (err)
return -EFAULT;
/* trampoline - the desired return ip is the retcode itself */
return_ip = (unsigned long)&frame->retcode;
/* This is:
l.ori r11,r0,__NR_sigreturn
l.sys 1
*/
err |= __put_user(0xa960, (short *)(frame->retcode + 0));
err |= __put_user(__NR_rt_sigreturn, (short *)(frame->retcode + 2));
err |= __put_user(0x20000001, (unsigned long *)(frame->retcode + 4));
err |= __put_user(0x15000000, (unsigned long *)(frame->retcode + 8));
if (err)
return -EFAULT;
/* Set up registers for signal handler */
regs->pc = (unsigned long)ksig->ka.sa.sa_handler; /* what we enter NOW */
regs->gpr[9] = (unsigned long)return_ip; /* what we enter LATER */
regs->gpr[3] = (unsigned long)ksig->sig; /* arg 1: signo */
regs->gpr[4] = (unsigned long)&frame->info; /* arg 2: (siginfo_t*) */
regs->gpr[5] = (unsigned long)&frame->uc; /* arg 3: ucontext */
/* actually move the usp to reflect the stacked frame */
regs->sp = (unsigned long)frame;
return 0;
}
static inline void
handle_signal(struct ksignal *ksig, struct pt_regs *regs)
{
int ret;
ret = setup_rt_frame(ksig, sigmask_to_save(), regs);
signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP));
}
/*
* Note that 'init' is a special process: it doesn't get signals it doesn't
* want to handle. Thus you cannot kill init even with a SIGKILL even by
* mistake.
*
* Also note that the regs structure given here as an argument, is the latest
* pushed pt_regs. It may or may not be the same as the first pushed registers
* when the initial usermode->kernelmode transition took place. Therefore
* we can use user_mode(regs) to see if we came directly from kernel or user
* mode below.
*/
int do_signal(struct pt_regs *regs, int syscall)
{
struct ksignal ksig;
unsigned long continue_addr = 0;
unsigned long restart_addr = 0;
unsigned long retval = 0;
int restart = 0;
if (syscall) {
continue_addr = regs->pc;
restart_addr = continue_addr - 4;
retval = regs->gpr[11];
/*
* Setup syscall restart here so that a debugger will
* see the already changed PC.
*/
switch (retval) {
case -ERESTART_RESTARTBLOCK:
restart = -2;
/* Fall through */
case -ERESTARTNOHAND:
case -ERESTARTSYS:
case -ERESTARTNOINTR:
restart++;
regs->gpr[11] = regs->orig_gpr11;
regs->pc = restart_addr;
break;
}
}
/*
* Get the signal to deliver. During the call to get_signal the
* debugger may change all our registers so we may need to revert
* the decision to restart the syscall; specifically, if the PC is
* changed, don't restart the syscall.
*/
if (get_signal(&ksig)) {
if (unlikely(restart) && regs->pc == restart_addr) {
if (retval == -ERESTARTNOHAND ||
retval == -ERESTART_RESTARTBLOCK
|| (retval == -ERESTARTSYS
&& !(ksig.ka.sa.sa_flags & SA_RESTART))) {
/* No automatic restart */
regs->gpr[11] = -EINTR;
regs->pc = continue_addr;
}
}
handle_signal(&ksig, regs);
} else {
/* no handler */
restore_saved_sigmask();
/*
* Restore pt_regs PC as syscall restart will be handled by
* kernel without return to userspace
*/
if (unlikely(restart) && regs->pc == restart_addr) {
regs->pc = continue_addr;
return restart;
}
}
return 0;
}
asmlinkage int
do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
{
do {
if (likely(thread_flags & _TIF_NEED_RESCHED)) {
schedule();
} else {
if (unlikely(!user_mode(regs)))
return 0;
local_irq_enable();
if (thread_flags & _TIF_SIGPENDING) {
int restart = do_signal(regs, syscall);
if (unlikely(restart)) {
/*
* Restart without handlers.
* Deal with it without leaving
* the kernel space.
*/
return restart;
}
syscall = 0;
} else {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
}
}
local_irq_disable();
thread_flags = current_thread_info()->flags;
} while (thread_flags & _TIF_WORK_MASK);
return 0;
}